Interlinked.

Explainers · updated July 2026

What is a context engine? The layer that decides what your AI sees.

A language model has no standing knowledge of your machine: not your repos, not your configs, not the document with the answer. Everything it appears to know about your code was selected, ranked, and pasted into its prompt a moment earlier. The system that does the selecting is the context engine. Get it right and the model feels omniscient; get it wrong and the smartest model on earth answers from the wrong three files. Cursor has one. Glean has one. Here is what they are, and the one your local machine is still missing.

The whole idea in one picture

A machine on one side. A sliver on the other.

Your machine holds millions of files. A prompt holds a handful. The context engine is the funnel between them: it takes a question and returns the small set of files, symbols, or lines most likely to answer it, small enough to fit the window. Everything downstream (the model's reasoning, the quality of the diff) is capped by what made it through. The engine is not a feature of the model. It is the gate in front of it.

YOUR MACHINE4.47M files, every repo+ the non-git 90% of the diskREPOS: they ship togetherDOCS & PDFsCONFIGS & .envDOWNLOADS · DATASETS · LOGSmillions, too big for any promptmillions inthe agent's question ↓THE CONTEXT ENGINEquestion → the right slice1 · FINDlocate every candidate2 · RANKwhich actually matter3 · ASSEMBLEfit the tiny windowa few files outTHE CONTEXT WINDOWonly a sliver fitsauth.tsconfig.json+ a couple moreEVERYTHING THE MODEL KNOWS ABOUT YOUR MACHINE CAME THROUGH HERE

The three jobs are always the same: find the candidates, rank what matters, assemble a slice that fits. Change the engine (its reach, its freshness, whether it guesses or proves) and you change the answer, on the exact same model.

Two you have already met

You have used a context engine. Probably two.

“Context engine” is not a marketing coinage: it names a real layer, and two of the best-known tools in software are built around it. They are drawn fairly here; both are good at the job they were built for. The point is only where each one's edge falls.

Cursor
For the repo you opened
a code index, in the editor
+Turns your open project into an index of meaning, so you can ask in plain English and get the right function without knowing its name.
+Re-reads only what you edit, so it keeps pace as you type.
+Exactly the right tool for working inside one codebase.
WHERE IT STOPS at the folder you opened. Sibling repos, and the files that were never in git, stay dark to it.
Glean
For your company's cloud
an enterprise work-AI engine
+Indexes an organization's SaaS apps (chat, drives, tickets, wikis) so a work assistant can answer from company knowledge.
+Permission-aware, so people only retrieve what they are allowed to see.
+The right tool for finding answers across a company's tools.
WHERE IT STOPS at the company's cloud apps. It needs a server, connectors, and an admin. And it is not the code on the machine in front of you.

Both prove the pattern. Both also stop at an edge: Cursor at one repo, Glean at the company's cloud. Neither is the machine you actually work on: the dozen repos that ship together, plus the non-git 90% (configs, documents, downloads, the PDF with the answer), fed to every agent, not just their own.

How to judge one

Four questions to ask any context engine.

Reach

What can it even see? One repo, one company's cloud, or the whole machine, every repo and the files git ignores?

Freshness

How current is the answer? This second, right after you save, or whenever it last re-indexed?

Trust

Is a hit a literal match you can verify, or a model's guess ranked by similarity, which drifts until re-computed?

Speed

Does it answer fast enough to live inside the agent's loop, or does every lookup stall the run?

Context engineReachFreshnessTrustSpeed
Cursorthe one repo you openedfresh as you typesemantic: ranked by meaningin-editor
Gleanyour company's cloud appsre-synced by connectorssemantic: ranked by meaningserver round-trip
Interlinkedwhole machine · every repo + non-git~1 ms after a saveliteral: exact, verifiable85 µs to 16 ms, local

Cursor and Glean are semantic engines: they retrieve by meaning, which is the right tool when you don't know the words. Interlinked is literal: exact, verifiable, whole-machine. Different jobs; they belong in the same stack. The row nobody had filled is the last one: a context engine that reaches the whole local machine, stays literal, refreshes on save, and answers fast enough to live inside the loop.

The local engine, measured · Ryzen 9 9950X3D · 4.47M files

Fast enough to live inside the loop.

139 µs
median filename lookup across 4.47M files (85 µs single file, best case 2 µs)
~8 ms
typical content query inside files (7 to 9 ms; ~16 ms exact phrases)
~1 ms
from saving a file to it being searchable (under 30 ms worst case)
The toolThe taskTimevs Interlinked
Interlinked (live index)one indexed lookup85 µsthe baseline
VS Code · Ctrl+Psame file, same drive35 s412,000×
Windows Searchmedian of 20 queries67 s~480,000×
ripgrep (content query)same query, same corpus93.8 s→ 16 ms

Same machine, same drive, same queries. On the content lane a query that took ripgrep 93.8 s returned in 16 ms, and across the five-query set, 58,625× faster than ripgrep.

WHAT THAT BUYS AN AGENT: ONE REAL TASK
6m 57s → 16ms
time for Claude Code to find one file: before, then with the engine
71 → 1
tool calls spent hunting for it
~58% → ~0%
session tokens burned on file search

Methodology: Ryzen 9 9950X3D · 64 GB DDR5 · NVMe · Windows 11 · 4,470,000 files. Filename figures are medians: 139 µs across 20 queries, 85 µs single-file; content queries run ~7 to 9 ms, ~16 ms for exact phrases. At rest the engine sits around 44 MB in Task Manager, and the on-disk index stays under 1% of the drive (~24 GB on a 4 TB machine).

The context engine for the machine in front of you

Cursor indexes a repo. Glean indexes a company. Interlinked indexes the machine, for every agent.

Interlinked is the context engine for the local machine: an always-fresh index of every file (names and contents) across every repo and the non-git 90%, exposed to whatever agent you use through one connector. No model in the box, so every hit is a literal match you can verify, not a ranked guess, and it never leaves the machine. The same index carries a relationship layer it builds by itself: which files change together, which repos ship together. The local analogue of the enterprise graph, seeded from your own history with zero LLMs. Keep Cursor's index. Keep Glean. This is the layer under both.

0 LLMs
every hit and every relationship is a literal match you can check: never a model's guess, nothing to drift
26,958 pairs
relationships seeded across 12 of 12 repos in 1.7 s on a fresh machine, from 8,455 git events, no model
19 clients
auto-configured in one install: Claude Code, Cursor, Copilot, Codex, Windsurf, Zed, Cline and the rest

PARALLEL TO CURSOR AND GLEAN · WHOLE-MACHINE · LOCAL · NO MODEL IN THE BOX.

Give every agent the whole machine

Put a real context engine under your agents.

1

Install once. One signed installer indexes every file on your machine and auto-configures 19 AI clients: Claude Code, Cursor, Codex, Windsurf, Zed, Cline and the rest. No JSON to edit, no cloud account, no keys.

2

Ask across the whole machine. Names, symbols, strings, error messages. Whole-machine, across every repo and the files git ignores, fresh to the last save. At rest the engine sits around 44 MB.

3

Keep your semantic engines. Cursor and Glean answer 'what is this about?' by meaning. Interlinked answers 'where is this exact thing, right now?' Different jobs, same stack.

4

Let the relationships grow. Day one it knows your git history: which repos ship together, which files move as a pair. Every agent reads it, no model in the loop.

Everything local is free forever, on all your devices, no card. Hosting starts at $5.99/mo. Download for Windows · RAG, a live index, or grep?

Measured July 2026 · Ryzen 9 9950X3D · 4.47M files · Windows 11← All research